Skip to Main Content (Press Enter)

Logo UNIMORE
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture
  • Terza Missione
  • Attività
  • Competenze

UNI-FIND
Logo UNIMORE

|

UNI-FIND

unimore.it
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture
  • Terza Missione
  • Attività
  • Competenze
  1. Pubblicazioni

Editing Everything Everywhere All at Once

Contributo in Atti di convegno
Data di Pubblicazione:
2026
Citazione:
Editing Everything Everywhere All at Once / Quattrini, F., Zaccagnino, C., Simsar, E., Tintoré Gazulla, M., Cucchiara, R., Tonioni, A., Cascianelli, S.. - (2026). (20th European Conference on Computer Vision, ECCV 2026 Malmö, Sweden SEP 8-OCT 12, 2024).
Abstract:
Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficiency and potentially better harmonization. However, when several instructions target different regions, semantic interference often leads to attribute leakage and poor edit disentanglement, especially as the number of edits increases. In this work, we propose MICE (Multi-Instance Concurrent Editing), a training-free strategy for scalable multi-instance image editing with Multimodal Diffusion Transformers. MICE modifies the additive bias of joint attention to regulate interactions between instance-specific edit instructions, latent, and context tokens identified via user-provided segmentation masks. Specifically, MICE allows intra-instance attention, penalizes interactions between neighboring region tokens, and suppresses unrelated cross-instance attention. As a result, our method enforces attribute binding while preserving global visual consistency. We evaluate MICE on LoMOE-Bench and introduce MICE-Bench, a more challenging benchmark with an average of 8.5 concurrent edits per image. The experiments demonstrate that our approach outperforms strong baselines and recent competitors in terms of visual quality preservation and faithfulness to the editing instructions.
Tipologia CRIS:
Relazione in Atti di Convegno
Elenco autori:
Quattrini, Fabio; Zaccagnino, Carmine; Simsar, Enis; Tintoré Gazulla, Marta; Cucchiara, Rita; Tonioni, Alessio; Cascianelli, Silvia
Autori di Ateneo:
CASCIANELLI Silvia
CUCCHIARA Rita
Link alla scheda completa:
https://iris.unimore.it/handle/11380/1414448
Titolo del libro:
COMPUTER VISION - ECCV 2026
Pubblicato in:
LECTURE NOTES IN COMPUTER SCIENCE
Journal
LECTURE NOTES IN COMPUTER SCIENCE
Series
  • Utilizzo dei cookie

Realizzato con VIVO | Designed by Cineca | 26.7.2.0